From 4fb1292c50dff8dfb4c4e54da4166a05ad929216 Mon Sep 17 00:00:00 2001
From: City <125218114+city96@users.noreply.github.com>
Date: Mon, 6 Nov 2023 23:25:49 +0100
Subject: [PATCH] Update README.md

---
 README.md | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/README.md b/README.md
index 9a74eaf..76fe833 100644
--- a/README.md
+++ b/README.md
@@ -31,6 +31,9 @@ Alternatively, use the manager, assuming it has an update function.
 
 
 ## DiT
+
+[Original Repo](https://github.com/facebookresearch/DiT)
+
 ### Model info / implementation
 - Uses class labels instead of prompts
 - Limited to 256x256 or 512x512 images
@@ -52,6 +55,9 @@ ConditioningCombine nodes *should* work for combining multiple labels. The area
 
 
 ## PixArt
+
+[Original Repo](https://github.com/PixArt-alpha/PixArt-alpha)
+
 ### Model info / implementation
 - Uses T5 text encoder instead of clip
 - Available in 512 and 1024 versions, needs specific pre-defined resolutions to work correctly
@@ -111,6 +117,17 @@ On windows, you may need a newer version of bitsandbytes for 4bit. Try `python -
 
 A few custom VAE models are supported. The option to select a different dtype when loading is also possible, which can be useful for testing/comparisons.
 
+### Consistency Decoder
+
+[Original Repo](https://github.com/openai/consistencydecoder)
+
+Proof of concept until [the model definitions are released](https://github.com/openai/consistencydecoder/issues/1)
+
+- Download the VAE from [the link in the OpenAI code](https://github.com/openai/consistencydecoder/blob/main/consistencydecoder/__init__.py#L79) / [Direct link](https://openaipublic.azureedge.net/diff-vae/c9cebd3132dd9c42936d803e33424145a748843c8f716c0814838bdc8a2fe7cb/decoder.pt)
+- Put the file in your VAE folder
+- Load it with the ExtraVAELoader
+- Run out of VRAM
+
 ### AutoencoderKL / VQModel
 
 `kl-f4/8/16/32` from the [compvis/latent diffusion repo](https://github.com/CompVis/latent-diffusion/tree/main#pretrained-autoencoding-models).